X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/b75c8c73cd7f3c92a16e03fb046f4e2a99363bc7..677a29545230804411babf7eefdbced18ffdd71d:/lib/bytes.pm

diff --git a/lib/bytes.pm b/lib/bytes.pm
index 3b0268e..918c8ee 100644
--- a/lib/bytes.pm
+++ b/lib/bytes.pm
@@ -1,6 +1,6 @@
 package bytes;
 
-our $VERSION = '1.00';
+our $VERSION = '1.04';
 
 $bytes::hint_bits = 0x00000008;
 
@@ -14,10 +14,17 @@ sub unimport {
 
 sub AUTOLOAD {
     require "bytes_heavy.pl";
-    goto &$AUTOLOAD;
+    goto &$AUTOLOAD if defined &$AUTOLOAD;
+    require Carp;
+    Carp::croak("Undefined subroutine $AUTOLOAD called");
 }
 
-sub length ($);
+sub length (_);
+sub chr (_);
+sub ord (_);
+sub substr ($$;$$);
+sub index ($$;$);
+sub rindex ($$;$);
 
 1;
 __END__
@@ -26,15 +33,31 @@ __END__
 
 bytes - Perl pragma to force byte semantics rather than character semantics
 
+=head1 DEPRECATED
+
+This pragma reflects early attempts to incorporate Unicode into perl and
+has since been superseded. It breaks encapsulation (i.e. it exposes the
+innards of how the perl executable currently happens to store a string),
+and use of this module for anything other than debugging purposes is
+strongly discouraged. If you feel that the functions here within might be
+useful for your application, this possibly indicates a mismatch beteen
+your mental model of Perl Unicode and the current reality. In that case,
+you may wish to peruse some of the perl Unicode documentation:
+L<perluniintro>, L<perlunitut>, L<perlunifaq> and L<perlunicode>.
+
 =head1 SYNOPSIS
 
     use bytes;
+    ... chr(...);       # or bytes::chr
+    ... index(...);     # or bytes::index
+    ... length(...);    # or bytes::length
+    ... ord(...);       # or bytes::ord
+    ... rindex(...);    # or bytes::rindex
+    ... substr(...);    # or bytes::substr
     no bytes;
 
-=head1 DESCRIPTION
 
-WARNING: The implementation of Unicode support in Perl is incomplete.
-See L<perlunicode> for the exact details.
+=head1 DESCRIPTION
 
 The C<use bytes> pragma disables character semantics for the rest of the
 lexical scope in which it appears.  C<no bytes> can be used to reverse
@@ -47,7 +70,7 @@ effect, the encoding is temporarily ignored, and each string is treated
 as a series of bytes. 
 
 As an example, when Perl sees C<$x = chr(400)>, it encodes the character
-in UTF8 and stores it in $x. Then it is marked as character data, so,
+in UTF-8 and stores it in $x. Then it is marked as character data, so,
 for instance, C<length $x> returns C<1>. However, in the scope of the
 C<bytes> pragma, $x is treated as a series of bytes - the bytes that make
 up the UTF8 encoding - and C<length $x> returns C<2>:
@@ -56,16 +79,22 @@ up the UTF8 encoding - and C<length $x> returns C<2>:
     print "Length is ", length $x, "\n";     # "Length is 1"
     printf "Contents are %vd\n", $x;         # "Contents are 400"
     { 
-        use bytes;
+        use bytes; # or "require bytes; bytes::length()"
         print "Length is ", length $x, "\n"; # "Length is 2"
         printf "Contents are %vd\n", $x;     # "Contents are 198.144"
     }
 
+chr(), ord(), substr(), index() and rindex() behave similarly.
+
 For more on the implications and differences between character
-semantics and byte semantics, see L<perlunicode>.
+semantics and byte semantics, see L<perluniintro> and L<perlunicode>.
+
+=head1 LIMITATIONS
+
+bytes::substr() does not work as an lvalue().
 
 =head1 SEE ALSO
 
-L<perlunicode>, L<utf8>
+L<perluniintro>, L<perlunicode>, L<utf8>
 
 =cut